Small Cell Lung Cancer

El Mehdi Baknine, s194533
Jakob Frostholm Højgaard, s194527
Jonathan Dragestad Møller, s184243
Mikkel Niklas Rasmussen, s193518
Thomas Malthe Mølgaard Tams, s204540

2023-11-28

Paper and data source

Title: Comprehensive genomic profiles of small cell lung cancer, George J. et. al. (2015)

Purpose: Identify different small cell lung cancer profiles

Data set overview

Loading

  • Dimensions: 81, 31669

  • 30 metadata

  • 31639 gene expression

Cleaning

  • New dimensions: 81, 31669

  • Check for duplicates in SampleIDs

  • Clean weird variables

  • Check NAs

Found NAs

# A tibble: 6 × 2
  name                             value
  <chr>                            <int>
1 pathology_review_3                  80
2 progression_free_survival_months    48
3 ethnicity                           39
4 smoking_history_pack_years          30
5 radiation_yes_no                    16
6 chemotherapy_yes_no                 12

Augmenting

  • New dimensions: 81, 433

Added variables

survival_time survival_status treatment_group
Good 0 Chemo and Radiation
Decent 0 Chemo Only
Good 0 Chemo and Radiation
Decent 0 Data Missing
Decent 0 Chemo and Radiation
Decent 0 Chemo and Radiation
Great 0 Chemo and Radiation
Decent 0 Chemo and Radiation
Good 1 Chemo and Radiation
Great 1 Chemo and Radiation
Good 1 Chemo and Radiation
Bad 0 Chemo Only
Great 0 Chemo and Radiation
Great 1 Data Missing
Great 0 Chemo Only
Decent 0 Chemo Only
Decent 0 No treatment
Decent 0 No treatment
NA NA Chemo and Radiation
Decent 0 Chemo and Radiation
NA NA Data Missing
Great 1 Chemo and Radiation
Terrible 1 Chemo and Radiation
Bad 0 Chemo Only
Good 1 No treatment
NA NA Data Missing
NA NA Data Missing
Decent 0 Chemo Only
Terrible 1 Data Missing
Decent 0 Chemo Only
Bad 0 Chemo and Radiation
Terrible 0 Radiation Only
Decent 0 Chemo and Radiation
Good 0 No treatment
Bad 0 Data Missing
Decent 0 Chemo and Radiation
Decent 1 All Treatments
Good 1 Data Missing
Decent 0 Chemo and Radiation
Terrible 0 Chemo and Radiation
Decent 0 Other Combinations
Decent 1 Chemo and Radiation
Terrible 0 No treatment
Terrible 0 No treatment
Terrible 0 No treatment
Great 1 Data Missing
Bad 0 Chemo and Radiation
Decent 1 Chemo and Radiation
Decent 0 Data Missing
Good 1 Chemo and Radiation
Bad 0 No treatment
Decent 0 Data Missing
Decent 0 Data Missing
Decent 0 Chemo and Radiation
Decent 0 Data Missing
Decent 0 Data Missing
Great 1 Chemo and Radiation
Good 0 Chemo and Radiation
Good 1 Chemo and Radiation
Decent 0 Data Missing
Terrible 0 Data Missing
Bad 0 Data Missing
Good 0 Chemo and Radiation
Great 1 Chemo and Radiation
Terrible 0 Data Missing
Great 1 Chemo and Radiation
Decent 1 Chemo and Radiation
Decent 1 Chemo and Radiation
Great 1 No treatment
Great 1 Chemo Only
Decent 0 No treatment
Great 1 No treatment
Bad 0 No treatment
Good 0 Chemo Only
Great 1 No treatment
Decent 1 No treatment
Decent 1 Chemo and Radiation
Decent 1 No treatment
Decent 1 Chemo and Radiation
Decent 0 Chemo and Radiation
Terrible 1 Other Combinations

Overview of metadata 1

Overview of metadata 2

Overview of metadata 3

Overview of metadata 4

Methods

submethod

K-means Hierchichal clustring t-test : N0 : There is no significant difference between clusters. To get low-high expression signature

Results

Executable Code

Plot1

Some exploratory data analysis

Conclusion